© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3769
    Prev
    Next
    INDEX
    Explanations

    varied, but focuses mostly on phrases used to compare something to something else.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FirebaseDatabase
    -0.55
     onItemClick
    -0.54
    WebServlet
    -0.49
     CURIAM
    -0.47
    快
    -0.46
    uyện
    -0.44
     Fasc
    -0.44
    Pair
    -0.44
    ướ
    -0.44
     فل
    -0.42
    POSITIVE LOGITS
    +#+#
    0.82
    migrationBuilder
    0.76
     кӀ
    0.68
     EconPapers
    0.68
    Vidite
    0.64
    Ārējās
    0.63
     esternos
    0.63
     &___
    0.63
    حياتها
    0.56
    تقاوى
    0.56
    Activations Density 1.936%

    No Known Activations